Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 294 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0600. Min Range: -5.0600

Max Act: 5.0600. Min Act: -0.1700

Data Index: 950054 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.7787. Min Act: -0.1700

Data Index: 1134863 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.5600. Min Act: -0.1700

Data Index: 366534 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.5912. Min Act: -0.1700

Data Index: 339737 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.5600. Min Act: -0.1700

Data Index: 431381 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4975. Min Act: -0.1700

Data Index: 177924 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4975. Min Act: -0.1700

Data Index: 164093 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4350. Min Act: -0.1700

Data Index: 106988 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4350. Min Act: -0.1700

Data Index: 1028245 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4037. Min Act: -0.1700

Data Index: 837869 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4037. Min Act: -0.1700

Data Index: 1167488 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4037. Min Act: -0.1700

Data Index: 1151258 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4037. Min Act: -0.1700

Data Index: 81358 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.3725. Min Act: -0.1700

Data Index: 788142 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.4037. Min Act: -0.1700

Data Index: 844967 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.3725. Min Act: -0.1700

Data Index: 77064 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.3412. Min Act: -0.1700

Data Index: 358181 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.3412. Min Act: -0.1700

Data Index: 544326 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.3412. Min Act: -0.1700

Data Index: 146501 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 5.0600. Min Range: -5.0600

Max Act: 4.3100. Min Act: -0.1700

Data Index: 453729 (C4 (Web Text))

Max Activating Token Index: 428